pith. sign in

Finding safety neurons in large language models.arXiv e-prints, pages arXiv–2406, 2024

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Alignment Dynamics in LLM Fine-Tuning

cs.LG · 2026-05-18 · unverdicted · novelty 6.0

The paper introduces a dynamical model that decomposes alignment updates in LLM fine-tuning into rebound and driving forces and predicts a rehearsal priming effect.

citing papers explorer

Showing 1 of 1 citing paper.

  • Alignment Dynamics in LLM Fine-Tuning cs.LG · 2026-05-18 · unverdicted · none · ref 48

    The paper introduces a dynamical model that decomposes alignment updates in LLM fine-tuning into rebound and driving forces and predicts a rehearsal priming effect.